Launches on September 18, 2026

Live tests for TypeSafe Jev (System One) via OpenRouter's Decisions API

weekend project using Jev to automate trace / data labeling for a provided labeling taxonomy.

Semantic lint CLI powered by TypeSafe Jev

Chrome extension using TypeSafe Jev.

MCP server exposing one tool: ask Jev a typed question and get a short answer back.

A completed experiment in letting TypeSafe's Jev play Balatro from structured game state. Includes the controller, companion mod, knowledge quizzes and playtest results.

Jev based detector and rewrite engine to censor profanity, rudeness and hate speech.

Feed triage prototype: TypeSafe Jev judgments tag posts by type, sentiment, and attention

Claude thinks, Jev reacts: an MCP server that hands browser tasks from Claude to TypeSafe's Jev (~100 ms per decision).

Express with no routes. TypeSafe Jev picks which handler runs.

What should a decision model be shown to play SameGame? 21 prompt strategies for TypeSafe's Jev, 76,795 logged requests and responses, reproducible tables. MIT.

Jev × 東京の防災電文 — 気象庁の防災情報XMLをリアルタイムに取り込み、TypeSafe の Jev が「自分にとって何を意味するか」を判定する Streamlit デモ

Claude Code skill: swap System 2 LLM pipeline components for System 1 TypeSafe Jev decisions via investigation, live three-arm eval, fallback, and an independent judge

Evaluating TypeSafe's Jev on Michael Mauboussin's 50-question decision calibration test

Resume-discovered project teams, scheduled by SolverForge.

AI moderator for Telegram groups powered by the Jev (TypeSafe System One) decision model

Testing TypeSafe's Jev model on real-time browser games (flappybird.io, play.tetris.com)

Testing typesafe.ai new model Jev

Cross-border B2B case triage prototype using TypeSafe Jev via OpenRouter

An inspired MECE map of TypeSafe Jev use cases from the first days on X

A realtime voice agent with no LLM in the loop: Deepgram Flux ends the turn, TypeSafe's Jev picks the reply, Deepgram Flux TTS speaks it.

Jev (TypeSafe System One) proof of concept: smart-home assistant demo

Score CSV/JSONL rows with TypeSafe Jev — YAML policies, calibrated confidence, auto/review/escalate

Automated PR review pipeline using Jev (TypeSafe AI) as a millisecond decision layer over an LLM reviewer

Which shell commands may your coding agent run without asking? An allowlist proves what it can; Jev, a no-text model, judges only the rest. Claude Code hook + CLI, measured.

Native Swift SDK for TypeSafe Jev System One decisions.

A bounded Pi execution supervisor powered by TypeSafe Jev: decisions, recovery, review and verification.

AI-powered jackpot number predictor and intelligence oracle built with TypeSafe System One (Jev)

Local-first visual decision debugger and regression testbench for TypeSafe AI Jev

⚡ Token Saver & Fast Decision Layer for OpenAI Codex — powered by Jev

A DarkOrbit-style space game piloted by Jev — TypeSafe's System One model. Three.js world, deterministic engine, Jev picks the targets.

One DevTool for any Jev-powered application. Inspect every state, question, probability, decision and action. Replay decisions locally.

jevzen: an MIT-licensed Chrome extension demo that switches unwanted X posts to zen or cat photos using TypeSafe Jev and Effect.

Jump to projects by description, powered by zoxide and TypeSafe’s Jev

Agent-friendly Go library and JSON-first CLI for TypeSafe AI's Jev and System One API

Krino (κρίνω) — probing, analysis, and replication toolkit for JEV-class decision models

Merge-gate triage for a red CI run: cluster the failures, let TypeSafe Jev label the cause, and return Gate: PASS (infra noise) or Gate: BLOCK (a real failure). Playwright, Jest, pytest.

Un harnais pour que Jev — un modèle qui ne sait que choisir — joue à Pokémon Bleu. Quand il boucle, il manque un champ.

A browser agent with no LLM in the loop — deterministic code plus Jev, a System One model. ~118ms per decision, typed and auditable.

Local-first skill router for coding agents. Inspired by TypeSafe Jev; optional swappable judge (not an official Jev product).

MOSS × Jev: a recorded-run 3D demo of the litter-picking rover choosing targets with TypeSafe's Jev decision model.

Natural-language command line suggestions for any CLI, powered by TypeSafe Jev (no LLM, ~0.5s)

System 1 (TypeSafe Jev) + System 2 (Octavus Platform) Dual-Brain Agent Architecture

Classify the Omarchy issue backlog with Jev, TypeSafe's System One model. Ten typed questions per issue in one request, for a hundredth of a cent each.

Native omp (oh-my-pi) extension: TypeSafe Jev judgment tools — token efficiency, confidence routing, citation verification

TypeSafe AI (Jev System One) plugin for OpenClaw - sub-100ms group triage, tool safety guardrails, compaction curation, and model routing

Open-source Jev-compatible MCP server for typed decisions (Choice/Score/Noul): local GLiNER backend with a model router, drop-in swappable with the TypeSafe System One API.

An agent in the browser that pays for thinking once: author a deterministic spec (Jev first, LLM on escalation), replay it for 0 tokens.

Agency-ready build prompt for a Personal Decision Inbox powered by TypeSafe AI (Jev). Full end-to-end spec: architecture, UI, integrations, deployment.

Shell command safety gate for the Pi coding agent, backed by TypeSafe's Jev judgment model